Fatema Bader Jasem
ABSTRACT
Trademarks and logos are used worldwide to represent companies, malls, shops and restaurants. It is one of the first visual symbols a company creates in the early stages of planning for this business. The logo must be unique and captures the idea of that business to make it easier for the common people to figure out what this business is about from the logo. With logos and trademarks details are very important where every element in the logo would make a difference including the colours used, shapes and fonts. Many efforts were made in last few years to detect, recognize or match similarities between logos; Moreover one of the major challenges faced was finding the correct dataset that include different local and international clear logos to test on . Thus, this paper presents a new dataset that would help in these types of machine learning project which provides 10K logo images with 2000 unique logo.
- Romberg, S., Pueyo, L. G., Lienhart, R., & Van Zwol, R. (2011). Scalable logo recognition in real-world images. In Proceedings of the 1st ACM International Conference on Multimedia Retrieval (pp. 1-8).Google Scholar
Digital Library
- Sage, A., Agustsson, E., Timofte, R., & Van Gool, L. (2018). Logo synthesis and manipulation with clustered generative adversarial networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5879-5888).Google ScholarCross Ref
- Su, H., Gong, S., & Zhu, X. (2017). Weblogo-2m: Scalable logo detection by deep learning from the web. In Proceedings of the IEEE International Conference on Computer Vision Workshops (pp. 270-279).Google ScholarCross Ref
- Tüzkö, A., Herrmann, C., Manger, D., & Beyerer, J. (2017). Open set logo detection and retrieval. arXiv preprint arXiv:1710.10891.Google Scholar
- Tursun, O., & Kalkan, S. (2015, May). Metu dataset: A big dataset for benchmarking trademark retrieval. In 2015 14th IAPR International Conference on Machine Vision Applications (MVA) (pp. 514-517). IEEE.Google ScholarCross Ref
- Su, H., Zhu, X., & Gong, S. (2018). Open logo detection challenge. arXiv preprint arXiv:1807.01964.Google Scholar
- Su, H., Zhu, X., & Gong, S. (2017, March). Deep learning logo detection with data expansion by synthesising context. In 2017 IEEE winter conference on applications of computer vision (WACV) (pp. 530-539). IEEE.Google Scholar
- Vinyals, O., Blundell, C., Lillicrap, T., & Wierstra, D. (2016). Matching networks for one shot learning. In Advances in neural information processing systems (pp. 3630-3638).Google Scholar
- Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., & Shah, R. (1994). Signature verification using a" siamese" time delay neural network. In Advances in neural information processing systems (pp. 737-744).Google Scholar
- Koch, G., Zemel, R., & Salakhutdinov, R. (2015, July). Siamese neural networks for one-shot image recognition. In ICML deep learning workshop (Vol. 2).Google Scholar
- Wiggers, K. L., Britto, A. S., Heutte, L., Koerich, A. L., & Oliveira, L. S. (2019, July). Image retrieval and pattern spotting using siamese neural network. In 2019 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.Google ScholarCross Ref
Recommendations
LogoDet-3K: A Large-scale Image Dataset for Logo Detection
Logo detection has been gaining considerable attention because of its wide range of applications in the multimedia field, such as copyright infringement detection, brand visibility monitoring, and product brand management on social media. In this article, ...
Blind Wavelet Based Logo Watermarking Resisting to Cropping
ICPR '10: Proceedings of the 2010 20th International Conference on Pattern RecognitionIn this paper we propose a blind wavelet-based logo watermarking scheme focusing on resisting to cropping. The binary logo is embedded in the LL2 sub-band of host image, using quantization technique. For increasing robustness of proposed algorithm two ...
A new robust adjustable logo watermarking scheme
In this paper, a novel, yet simple, watermarking algorithm for image authentication is proposed using fractional wavelet packet transform (FRWPT) via singular value decomposition (SVD). Unlike the traditional watermarking schemes where the watermark is ...
Comments